Did some work on a new high quality #nvda#tts engine for 2026. Unfortunately, I can’t get indexing to work. Even with AI. Help? Someone? It builds with scons. GitHub - fastfinge/supertonic-nvda: supertonic for nvda github.com/fastfinge/supertonic-nvda
@fastfinge More importantly, stopping speech doesn't work. Your approach seems to be wrong. The speak method runs in the main thread, and I assume synthesizing blocks.